
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt


train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
train.head()


train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1460 entries, 0 to 1459
Data columns (total 81 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   Id             1460 non-null   int64  
 1   MSSubClass     1460 non-null   int64  
 2   MSZoning       1460 non-null   object 
 3   LotFrontage    1201 non-null   float64
 4   LotArea        1460 non-null   int64  
 5   Street         1460 non-null   object 
 6   Alley          91 non-null     object 
 7   LotShape       1460 non-null   object 
 8   LandContour    1460 non-null   object 
 9   Utilities      1460 non-null   object 
 10  LotConfig      1460 non-null   object 
 11  LandSlope      1460 non-null   object 
 12  Neighborhood   1460 non-null   object 
 13  Condition1     1460 non-null   object 
 14  Condition2     1460 non-null   object 
 15  BldgType       1460 non-null   object 
 16  HouseStyle     1460 non-null   object 
 17  OverallQual    1460 non-null   int64  
 18  OverallCond    1460 non-null   int64  
 19  YearBuilt      1460 non-null   int64  
 20  YearRemodAdd   1460 non-null   int64  
 21  RoofStyle      1460 non-null   object 
 22  RoofMatl       1460 non-null   object 
 23  Exterior1st    1460 non-null   object 
 24  Exterior2nd    1460 non-null   object 
 25  MasVnrType     1452 non-null   object 
 26  MasVnrArea     1452 non-null   float64
 27  ExterQual      1460 non-null   object 
 28  ExterCond      1460 non-null   object 
 29  Foundation     1460 non-null   object 
 30  BsmtQual       1423 non-null   object 
 31  BsmtCond       1423 non-null   object 
 32  BsmtExposure   1422 non-null   object 
 33  BsmtFinType1   1423 non-null   object 
 34  BsmtFinSF1     1460 non-null   int64  
 35  BsmtFinType2   1422 non-null   object 
 36  BsmtFinSF2     1460 non-null   int64  
 37  BsmtUnfSF      1460 non-null   int64  
 38  TotalBsmtSF    1460 non-null   int64  
 39  Heating        1460 non-null   object 
 40  HeatingQC      1460 non-null   object 
 41  CentralAir     1460 non-null   object 
 42  Electrical     1459 non-null   object 
 43  1stFlrSF       1460 non-null   int64  
 44  2ndFlrSF       1460 non-null   int64  
 45  LowQualFinSF   1460 non-null   int64  
 46  GrLivArea      1460 non-null   int64  
 47  BsmtFullBath   1460 non-null   int64  
 48  BsmtHalfBath   1460 non-null   int64  
 49  FullBath       1460 non-null   int64  
 50  HalfBath       1460 non-null   int64  
 51  BedroomAbvGr   1460 non-null   int64  
 52  KitchenAbvGr   1460 non-null   int64  
 53  KitchenQual    1460 non-null   object 
 54  TotRmsAbvGrd   1460 non-null   int64  
 55  Functional     1460 non-null   object 
 56  Fireplaces     1460 non-null   int64  
 57  FireplaceQu    770 non-null    object 
 58  GarageType     1379 non-null   object 
 59  GarageYrBlt    1379 non-null   float64
 60  GarageFinish   1379 non-null   object 
 61  GarageCars     1460 non-null   int64  
 62  GarageArea     1460 non-null   int64  
 63  GarageQual     1379 non-null   object 
 64  GarageCond     1379 non-null   object 
 65  PavedDrive     1460 non-null   object 
 66  WoodDeckSF     1460 non-null   int64  
 67  OpenPorchSF    1460 non-null   int64  
 68  EnclosedPorch  1460 non-null   int64  
 69  3SsnPorch      1460 non-null   int64  
 70  ScreenPorch    1460 non-null   int64  
 71  PoolArea       1460 non-null   int64  
 72  PoolQC         7 non-null      object 
 73  Fence          281 non-null    object 
 74  MiscFeature    54 non-null     object 
 75  MiscVal        1460 non-null   int64  
 76  MoSold         1460 non-null   int64  
 77  YrSold         1460 non-null   int64  
 78  SaleType       1460 non-null   object 
 79  SaleCondition  1460 non-null   object 
 80  SalePrice      1460 non-null   int64  
dtypes: float64(3), int64(35), object(43)
memory usage: 924.0+ KB


train.describe()


def nanPercent(data, column):
    return data[column].isna().sum() / len(data[column]) * 100


columns = train.columns
for col in columns:
    print("Non-null", col, "=", nanPercent(train, col), "%")

Non-null Id = 0.0 %
Non-null MSSubClass = 0.0 %
Non-null MSZoning = 0.0 %
Non-null LotFrontage = 17.73972602739726 %
Non-null LotArea = 0.0 %
Non-null Street = 0.0 %
Non-null Alley = 93.76712328767123 %
Non-null LotShape = 0.0 %
Non-null LandContour = 0.0 %
Non-null Utilities = 0.0 %
Non-null LotConfig = 0.0 %
Non-null LandSlope = 0.0 %
Non-null Neighborhood = 0.0 %
Non-null Condition1 = 0.0 %
Non-null Condition2 = 0.0 %
Non-null BldgType = 0.0 %
Non-null HouseStyle = 0.0 %
Non-null OverallQual = 0.0 %
Non-null OverallCond = 0.0 %
Non-null YearBuilt = 0.0 %
Non-null YearRemodAdd = 0.0 %
Non-null RoofStyle = 0.0 %
Non-null RoofMatl = 0.0 %
Non-null Exterior1st = 0.0 %
Non-null Exterior2nd = 0.0 %
Non-null MasVnrType = 0.547945205479452 %
Non-null MasVnrArea = 0.547945205479452 %
Non-null ExterQual = 0.0 %
Non-null ExterCond = 0.0 %
Non-null Foundation = 0.0 %
Non-null BsmtQual = 2.5342465753424657 %
Non-null BsmtCond = 2.5342465753424657 %
Non-null BsmtExposure = 2.6027397260273974 %
Non-null BsmtFinType1 = 2.5342465753424657 %
Non-null BsmtFinSF1 = 0.0 %
Non-null BsmtFinType2 = 2.6027397260273974 %
Non-null BsmtFinSF2 = 0.0 %
Non-null BsmtUnfSF = 0.0 %
Non-null TotalBsmtSF = 0.0 %
Non-null Heating = 0.0 %
Non-null HeatingQC = 0.0 %
Non-null CentralAir = 0.0 %
Non-null Electrical = 0.0684931506849315 %
Non-null 1stFlrSF = 0.0 %
Non-null 2ndFlrSF = 0.0 %
Non-null LowQualFinSF = 0.0 %
Non-null GrLivArea = 0.0 %
Non-null BsmtFullBath = 0.0 %
Non-null BsmtHalfBath = 0.0 %
Non-null FullBath = 0.0 %
Non-null HalfBath = 0.0 %
Non-null BedroomAbvGr = 0.0 %
Non-null KitchenAbvGr = 0.0 %
Non-null KitchenQual = 0.0 %
Non-null TotRmsAbvGrd = 0.0 %
Non-null Functional = 0.0 %
Non-null Fireplaces = 0.0 %
Non-null FireplaceQu = 47.26027397260274 %
Non-null GarageType = 5.5479452054794525 %
Non-null GarageYrBlt = 5.5479452054794525 %
Non-null GarageFinish = 5.5479452054794525 %
Non-null GarageCars = 0.0 %
Non-null GarageArea = 0.0 %
Non-null GarageQual = 5.5479452054794525 %
Non-null GarageCond = 5.5479452054794525 %
Non-null PavedDrive = 0.0 %
Non-null WoodDeckSF = 0.0 %
Non-null OpenPorchSF = 0.0 %
Non-null EnclosedPorch = 0.0 %
Non-null 3SsnPorch = 0.0 %
Non-null ScreenPorch = 0.0 %
Non-null PoolArea = 0.0 %
Non-null PoolQC = 99.52054794520548 %
Non-null Fence = 80.75342465753424 %
Non-null MiscFeature = 96.30136986301369 %
Non-null MiscVal = 0.0 %
Non-null MoSold = 0.0 %
Non-null YrSold = 0.0 %
Non-null SaleType = 0.0 %
Non-null SaleCondition = 0.0 %
Non-null SalePrice = 0.0 %


plt.rcParams['font.size'] = 50 # use http://alanpryorjr.com/visualizations/seaborn/heatmap/heatmap/
fig, ax = plt.subplots(figsize = (50, 50))
sns.heatmap(train.corr(), annot=True, annot_kws={"size": 20}, linewidths=.5, ax=ax) # Use from https://stackoverflow.com/questions/38913965/make-the-size-of-a-heatmap-bigger-with-seaborn

<matplotlib.axes._subplots.AxesSubplot at 0x7f2bb1542dc0>


relatedFeatures = 4
top4 = train.corr().SalePrice.sort_values(ascending = False)[1:relatedFeatures + 1]
print(top4)
top4Names = top4.index

OverallQual    0.790982
GrLivArea      0.708624
GarageCars     0.640409
GarageArea     0.623431
Name: SalePrice, dtype: float64


import math
logTrain = train.copy()
logTrain['SalePrice'] = np.log(logTrain['SalePrice'])


plt.rcParams['font.size'] = 50 # use http://alanpryorjr.com/visualizations/seaborn/heatmap/heatmap/
fig, ax = plt.subplots(figsize = (50, 50))
sns.heatmap(logTrain.corr(), annot=True, annot_kws={"size": 20}, linewidths=.5, ax=ax) # Use from https://stackoverflow.com/questions/38913965/make-the-size-of-a-heatmap-bigger-with-seaborn
plt.rcParams['font.size'] = 15


train.corr().SalePrice.sort_values(ascending = False)

SalePrice        1.000000
OverallQual      0.790982
GrLivArea        0.708624
GarageCars       0.640409
GarageArea       0.623431
TotalBsmtSF      0.613581
1stFlrSF         0.605852
FullBath         0.560664
TotRmsAbvGrd     0.533723
YearBuilt        0.522897
YearRemodAdd     0.507101
GarageYrBlt      0.486362
MasVnrArea       0.477493
Fireplaces       0.466929
BsmtFinSF1       0.386420
LotFrontage      0.351799
WoodDeckSF       0.324413
2ndFlrSF         0.319334
OpenPorchSF      0.315856
HalfBath         0.284108
LotArea          0.263843
BsmtFullBath     0.227122
BsmtUnfSF        0.214479
BedroomAbvGr     0.168213
ScreenPorch      0.111447
PoolArea         0.092404
MoSold           0.046432
3SsnPorch        0.044584
BsmtFinSF2      -0.011378
BsmtHalfBath    -0.016844
MiscVal         -0.021190
Id              -0.021917
LowQualFinSF    -0.025606
YrSold          -0.028923
OverallCond     -0.077856
MSSubClass      -0.084284
EnclosedPorch   -0.128578
KitchenAbvGr    -0.135907
Name: SalePrice, dtype: float64


logTrain.corr().SalePrice.sort_values(ascending = False)

SalePrice        1.000000
OverallQual      0.817184
GrLivArea        0.700927
GarageCars       0.680625
GarageArea       0.650888
TotalBsmtSF      0.612134
1stFlrSF         0.596981
FullBath         0.594771
YearBuilt        0.586570
YearRemodAdd     0.565608
GarageYrBlt      0.541073
TotRmsAbvGrd     0.534422
Fireplaces       0.489449
MasVnrArea       0.430809
BsmtFinSF1       0.372023
LotFrontage      0.355878
WoodDeckSF       0.334135
OpenPorchSF      0.321053
2ndFlrSF         0.319300
HalfBath         0.313982
LotArea          0.257320
BsmtFullBath     0.236224
BsmtUnfSF        0.221985
BedroomAbvGr     0.209044
ScreenPorch      0.121208
PoolArea         0.069798
MoSold           0.057329
3SsnPorch        0.054900
BsmtFinSF2       0.004832
BsmtHalfBath    -0.005149
Id              -0.017942
MiscVal         -0.020021
OverallCond     -0.036868
YrSold          -0.037263
LowQualFinSF    -0.037963
MSSubClass      -0.073959
KitchenAbvGr    -0.147548
EnclosedPorch   -0.149050
Name: SalePrice, dtype: float64


def numericalFeaturePlots(featureName, targetName, data):
    fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(27, 10))
    fig.suptitle('Plots of feature ' + featureName)
    ax1.hexbin(data[featureName], data[targetName])
    ax2.scatter(data[featureName], data[targetName])


target = "SalePrice"
for name in top4Names:
    numericalFeaturePlots(name, target, train)


def categoricalFeaturePlots(featureName, targetName, data):
    plt.rcParams['font.size'] = 19
    fig, ax = plt.subplots(1, 1, figsize=(27, 10))
    fig.suptitle('Plots of feature ' + featureName)
    ax.scatter(data[featureName], data[targetName])


categoricalFeatures = ["MSZoning", "Neighborhood", "SaleCondition"]
for feature in categoricalFeatures:
    categoricalFeaturePlots(feature, target, train)


sns.set() # Use from https://www.kaggle.com/pmarcelino/comprehensive-data-exploration-with-python
cols = ['SalePrice', 'OverallQual', 'GrLivArea', 'GarageCars', 'TotalBsmtSF', 'FullBath', 'YearBuilt']
sns.pairplot(train[cols])

<seaborn.axisgrid.PairGrid at 0x7f2bb0aec580>


nan = pd.Series(dtype='float64');
for col in columns:
    nan[col] = nanPercent(train, col)
nan = nan.sort_values()
for feature in nan.index:
    if nan[feature] != 0:
        print(feature, '\t', nan[feature])

Electrical 	 0.0684931506849315
MasVnrType 	 0.547945205479452
MasVnrArea 	 0.547945205479452
BsmtQual 	 2.5342465753424657
BsmtCond 	 2.5342465753424657
BsmtFinType1 	 2.5342465753424657
BsmtFinType2 	 2.6027397260273974
BsmtExposure 	 2.6027397260273974
GarageQual 	 5.5479452054794525
GarageFinish 	 5.5479452054794525
GarageYrBlt 	 5.5479452054794525
GarageType 	 5.5479452054794525
GarageCond 	 5.5479452054794525
LotFrontage 	 17.73972602739726
FireplaceQu 	 47.26027397260274
Fence 	 80.75342465753424
Alley 	 93.76712328767123
MiscFeature 	 96.30136986301369
PoolQC 	 99.52054794520548


train.head()


featuresWithoutNA = ["PoolQC", "MiscFeature", "Fence",  "FireplaceQu", "GarageCond", "GarageType", "GarageFinish", "GarageQual", "BsmtExposure", "BsmtFinType1", "BsmtFinType2", "BsmtCond", "BsmtQual", "MasVnrType"]
hasNA = False
for feature in featuresWithoutNA:
    if len(train.loc[train[feature] == "NA"]) > 0:
        hasNA = True
        break
if hasNA:
    print("Some features of selected features has at least one row with NA.")
else:
    print("None of selected features has a row with NA.")

None of selected features has a row with NA.


for feature in featuresWithoutNA:
    train.loc[train[feature].isna(), feature] = "NA"
    #print(feature, nanPercent(train, feature))


train.head()


train = train.drop(labels=['Alley'], axis=1)


meanFeature = ["LotFrontage", "GarageYrBlt", "MasVnrArea"]
for feature in meanFeature:
    train[feature].fillna(train[feature].mean(), inplace = True)


train = train[train.Electrical.isna() == False]


nan = pd.Series(dtype='float64');
columns = train.columns
for col in columns:
    nan[col] = nanPercent(train, col)
nan = nan.sort_values()
for feature in nan.index:
    if nan[feature] != 0:
        print(feature, '\t', nan[feature])


from sklearn.preprocessing import StandardScaler
numCols = train.columns[train.dtypes.apply(lambda c: np.issubdtype(c, np.number))]
numCols = numCols[1:-1] #Remove id and SalePrice
print(numCols)

scaler = StandardScaler()
train[numCols] = scaler.fit_transform(train[numCols])

Index(['MSSubClass', 'LotFrontage', 'LotArea', 'OverallQual', 'OverallCond',
       'YearBuilt', 'YearRemodAdd', 'MasVnrArea', 'BsmtFinSF1', 'BsmtFinSF2',
       'BsmtUnfSF', 'TotalBsmtSF', '1stFlrSF', '2ndFlrSF', 'LowQualFinSF',
       'GrLivArea', 'BsmtFullBath', 'BsmtHalfBath', 'FullBath', 'HalfBath',
       'BedroomAbvGr', 'KitchenAbvGr', 'TotRmsAbvGrd', 'Fireplaces',
       'GarageYrBlt', 'GarageCars', 'GarageArea', 'WoodDeckSF', 'OpenPorchSF',
       'EnclosedPorch', '3SsnPorch', 'ScreenPorch', 'PoolArea', 'MiscVal',
       'MoSold', 'YrSold'],
      dtype='object')


train.head()


type(train.SalePrice[0])

numpy.int64


train.head()


normalizedTrain.columns

Index(['1stFlrSF', '2ndFlrSF', '3SsnPorch', 'BedroomAbvGr', 'BldgType',
       'BsmtCond', 'BsmtExposure', 'BsmtFinSF1', 'BsmtFinSF2', 'BsmtFinType1',
       'BsmtFinType2', 'BsmtFullBath', 'BsmtHalfBath', 'BsmtQual', 'BsmtUnfSF',
       'CentralAir', 'Condition1', 'Condition2', 'Electrical', 'EnclosedPorch',
       'ExterCond', 'ExterQual', 'Exterior1st', 'Exterior2nd', 'Fence',
       'FireplaceQu', 'Fireplaces', 'Foundation', 'FullBath', 'Functional',
       'GarageArea', 'GarageCars', 'GarageCond', 'GarageFinish', 'GarageQual',
       'GarageType', 'GarageYrBlt', 'GrLivArea', 'HalfBath', 'Heating',
       'HeatingQC', 'HouseStyle', 'Id', 'KitchenAbvGr', 'KitchenQual',
       'LandContour', 'LandSlope', 'LotArea', 'LotConfig', 'LotFrontage',
       'LotShape', 'LowQualFinSF', 'MSSubClass', 'MSZoning', 'MasVnrArea',
       'MasVnrType', 'MiscFeature', 'MiscVal', 'MoSold', 'Neighborhood',
       'OpenPorchSF', 'OverallCond', 'OverallQual', 'PavedDrive', 'PoolArea',
       'PoolQC', 'RoofMatl', 'RoofStyle', 'SaleCondition', 'SalePrice',
       'SaleType', 'ScreenPorch', 'Street', 'TotRmsAbvGrd', 'TotalBsmtSF',
       'Utilities', 'WoodDeckSF', 'YearBuilt', 'YearRemodAdd', 'YrSold'],
      dtype='object')


train = train.drop(labels=['LotFrontage', 'WoodDeckSF', 'OpenPorchSF', '2ndFlrSF',\
                          'HalfBath', 'LotArea', 'BsmtFullBath', 'BsmtUnfSF',\
                          'BedroomAbvGr', 'ScreenPorch', 'PoolArea', 'MoSold',\
                          '3SsnPorch', 'BsmtFinSF2', 'BsmtHalfBath', 'MiscVal',\
                          'OverallCond', 'YrSold', 'LowQualFinSF', 'MSSubClass',\
                          'KitchenAbvGr', 'EnclosedPorch', 'LotShape', 'LandContour',\
                          'LotConfig', 'LandSlope', 'Condition1', 'Condition2', 'RoofStyle',\
                          'Exterior1st', 'Exterior2nd', 'MasVnrType', 'Foundation',\
                          'BsmtFinType1', 'BsmtFinType2', 'Electrical', 'GarageType',\
                          'GarageFinish', 'PavedDrive', 'MiscFeature', 'Fence', 'PoolQC',\
                          'GarageCond', 'HouseStyle', 'BsmtCond', 'BldgType', 'RoofMatl',\
                          'Heating'], axis=1)


train.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1459 entries, 0 to 1459
Data columns (total 32 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   Id             1459 non-null   int64  
 1   MSZoning       1459 non-null   object 
 2   Street         1459 non-null   object 
 3   Utilities      1459 non-null   object 
 4   Neighborhood   1459 non-null   object 
 5   OverallQual    1459 non-null   float64
 6   YearBuilt      1459 non-null   float64
 7   YearRemodAdd   1459 non-null   float64
 8   MasVnrArea     1459 non-null   float64
 9   ExterQual      1459 non-null   object 
 10  ExterCond      1459 non-null   object 
 11  BsmtQual       1459 non-null   object 
 12  BsmtExposure   1459 non-null   object 
 13  BsmtFinSF1     1459 non-null   float64
 14  TotalBsmtSF    1459 non-null   float64
 15  HeatingQC      1459 non-null   object 
 16  CentralAir     1459 non-null   object 
 17  1stFlrSF       1459 non-null   float64
 18  GrLivArea      1459 non-null   float64
 19  FullBath       1459 non-null   float64
 20  KitchenQual    1459 non-null   object 
 21  TotRmsAbvGrd   1459 non-null   float64
 22  Functional     1459 non-null   object 
 23  Fireplaces     1459 non-null   float64
 24  FireplaceQu    1459 non-null   object 
 25  GarageYrBlt    1459 non-null   float64
 26  GarageCars     1459 non-null   float64
 27  GarageArea     1459 non-null   float64
 28  GarageQual     1459 non-null   object 
 29  SaleType       1459 non-null   object 
 30  SaleCondition  1459 non-null   object 
 31  SalePrice      1459 non-null   int64  
dtypes: float64(14), int64(2), object(16)
memory usage: 376.1+ KB


# Ordinal Feature Encoding
from sklearn.preprocessing import LabelEncoder
ordinalFeatures = ['Utilities', 'ExterQual', 'ExterCond', 'BsmtQual', 'BsmtExposure', 'HeatingQC',\
                  'HeatingQC', 'CentralAir', 'KitchenQual', 'FireplaceQu', 'GarageQual']
for feature in ordinalFeatures:
    labelEncoder = LabelEncoder()
    train[feature] = labelEncoder.fit_transform(train[feature])
    
# Nominal Feature
nominalFeature = ['MSZoning', 'Street', 'Neighborhood', 'Functional', 'SaleType', 'SaleCondition']
for feature in nominalFeature:
    oneHot = pd.get_dummies(train[feature], drop_first=True)
    train = train.drop(feature, axis = 1)
    train = train.join(oneHot)


from sklearn.model_selection import train_test_split
trainSp, testSp = train_test_split(train, test_size=0.20, random_state=42)
trainSp.head()


testSp.head()


print(len(trainSp), len(testSp))

1167 292


from sklearn.neighbors import KNeighborsRegressor
from sklearn.metrics import mean_squared_error, mean_absolute_error
minErrorMSE = 100000000000
minErrorMAE = 100000000000
idMinMSE = 1
idMinMAE = 1
MSElist = []
MAElist = []
MSElistTrain = []
MAElistTrain = []
X = trainSp.drop('SalePrice', axis=1)
y = trainSp.SalePrice
Xtest = testSp.drop('SalePrice', axis=1)
for neighbors in range(1, 100):
    neigh = KNeighborsRegressor(n_neighbors=neighbors)
    neigh.fit(X, y)
    predict = neigh.predict(Xtest)
    predictTrain = neigh.predict(X)
    MSE = mean_squared_error(testSp.SalePrice, predict)
    MAE = mean_absolute_error(testSp.SalePrice, predict)
    MSElist.append(MSE**0.5)
    MAElist.append(MAE)
    MSElistTrain.append(mean_squared_error(y, predictTrain)**0.5)
    MAElistTrain.append(mean_absolute_error(y, predictTrain))
    if MSE < minErrorMSE:
        minErrorMSE = MSE
        idMinMSE = neighbors
    if MAE < minErrorMAE:
        minErrorMAE = MAE
        idMinMAE = neighbors
print("Min MAE is", minErrorMAE, "with", idMinMAE, "n_neighbors")
print("Min RMSE is", minErrorMSE ** 0.5, "with", idMinMSE, "n_neighbors")
p1, = plt.plot(MSElist, label="RMSETest")
p2, = plt.plot(MAElist, label="MAETest")
p3, = plt.plot(MSElistTrain, label="RMSETrain")
p4, = plt.plot(MAElistTrain, label="MAETrain")
plt.legend(handles=[p1, p2, p3, p4])

Min MAE is 39484.7796803653 with 3 n_neighbors
Min RMSE is 55100.0724917446 with 3 n_neighbors

<matplotlib.legend.Legend at 0x7f2bb0edc5e0>


from sklearn.tree import DecisionTreeRegressor
minErrorMSE = 100000000000
minErrorMAE = 100000000000
idMinMSE = 1
idMinMAE = 1
MSElist = []
MAElist = []
MSElistTrain = []
MAElistTrain = []
X = trainSp.drop('SalePrice', axis=1)
y = trainSp.SalePrice
Xtest = testSp.drop('SalePrice', axis=1)
for maxDepth in range(1, 200):
    clf = DecisionTreeRegressor(random_state=23, max_depth=maxDepth)
    clf.fit(X, y)
    predict = clf.predict(Xtest)
    predictTrain = clf.predict(X)
    MSE = mean_squared_error(testSp.SalePrice, predict)
    MAE = mean_absolute_error(testSp.SalePrice, predict)
    MSElist.append(MSE**0.5)
    MAElist.append(MAE)
    MSElistTrain.append(mean_squared_error(y, predictTrain)**0.5)
    MAElistTrain.append(mean_absolute_error(y, predictTrain))
    if MSE < minErrorMSE:
        minErrorMSE = MSE
        idMinMSE = maxDepth
    if MAE < minErrorMAE:
        minErrorMAE = MAE
        idMinMAE = maxDepth
print("Min MAE is", minErrorMAE, "with", idMinMAE, "max_depth")
print("Min RMSE is", minErrorMSE ** 0.5, "with", idMinMSE, "max_depth")
p1, = plt.plot(MSElist, label="RMSETest")
p2, = plt.plot(MAElist, label="MAETest")
p3, = plt.plot(MSElistTrain, label="RMSETrain")
p4, = plt.plot(MAElistTrain, label="MAETrain")
plt.legend(handles=[p1, p2, p3, p4])

Min MAE is 23191.15201214311 with 14 max_depth
Min RMSE is 32847.90312190818 with 7 max_depth

<matplotlib.legend.Legend at 0x7f2bb0ed3a30>


from sklearn.linear_model import LinearRegression
lr = LinearRegression()
X = trainSp.drop('SalePrice', axis=1)
y = trainSp.SalePrice
lr.fit(X, y)
MSE = mean_squared_error(testSp.SalePrice, lr.predict(testSp.drop('SalePrice', axis=1)))
MAE = mean_absolute_error(testSp.SalePrice, lr.predict(testSp.drop('SalePrice', axis=1)))
print("MAE is", MAE)
print("RMSE is", MSE ** 0.5)

MAE is 18419.597925250404
RMSE is 24617.577917692688


from sklearn.ensemble import RandomForestRegressor
minErrorMSE = 100000000000
minErrorMAE = 100000000000
X = trainSp.drop('SalePrice', axis=1)
y = trainSp.SalePrice
Xtest = testSp.drop('SalePrice', axis=1)
for maxDepth in range(20, 30):
    for nEstimators in range(100, 115):
        clf = RandomForestRegressor(random_state=23, max_depth=maxDepth, n_estimators=nEstimators)        
        clf.fit(X, y)
        predict = clf.predict(Xtest)
        MSE = mean_squared_error(testSp.SalePrice, predict)
        MAE = mean_absolute_error(testSp.SalePrice, predict)
        MSElist.append(MSE**0.5)
        MAElist.append(MAE)
        if MSE < minErrorMSE:
            minErrorMSE = MSE
        if MAE < minErrorMAE:
            minErrorMAE = MAE
print("Min MAE is", minErrorMAE)
print("Min RMSE is", minErrorMSE ** 0.5)

Min MAE is 17245.441317105015
Min RMSE is 24981.764721501444


from sklearn.ensemble import VotingRegressor
neigh = KNeighborsRegressor(n_neighbors=3)
clf = DecisionTreeRegressor(random_state=23, max_depth=14)
lre = LinearRegression()
er = VotingRegressor([('ne', neigh), ('cl', clf), ('lr', lre)])
X = trainSp.drop('SalePrice', axis=1)
y = trainSp.SalePrice
er.fit(X, y)
predict = er.predict(testSp.drop('SalePrice', axis=1))
MSE = mean_squared_error(testSp.SalePrice, predict)
MAE = mean_absolute_error(testSp.SalePrice, predict)
print("MAE is", MAE)
print("RMSE is", MSE ** 0.5)

MAE is 19865.8519179012
RMSE is 28072.13323416943

	Id	MSSubClass	MSZoning	LotFrontage	LotArea	Street	Alley	LotShape	LandContour	Utilities	...	PoolQC	Fence	MiscFeature	MoSold	YrSold	SaleType	SaleCondition	SalePrice
0	1	60	RL	65.0	8450	Pave	NaN	Reg	Lvl	AllPub	...	NaN	NaN	NaN	2	2008	WD	Normal	208500
1	2	20	RL	80.0	9600	Pave	NaN	Reg	Lvl	AllPub	...	NaN	NaN	NaN	5	2007	WD	Normal	181500
2	3	60	RL	68.0	11250	Pave	NaN	IR1	Lvl	AllPub	...	NaN	NaN	NaN	9	2008	WD	Normal	223500
3	4	70	RL	60.0	9550	Pave	NaN	IR1	Lvl	AllPub	...	NaN	NaN	NaN	2	2006	WD	Abnorml	140000
4	5	60	RL	84.0	14260	Pave	NaN	IR1	Lvl	AllPub	...	NaN	NaN	NaN	12	2008	WD	Normal	250000

	Id	MSSubClass	LotFrontage	LotArea	OverallQual	OverallCond	YearBuilt	YearRemodAdd	MasVnrArea	BsmtFinSF1	...	WoodDeckSF	OpenPorchSF	EnclosedPorch	3SsnPorch	ScreenPorch	PoolArea	MiscVal	MoSold	YrSold	SalePrice
count	1460.000000	1460.000000	1201.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1452.000000	1460.000000	...	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000	1460.000000
mean	730.500000	56.897260	70.049958	10516.828082	6.099315	5.575342	1971.267808	1984.865753	103.685262	443.639726	...	94.244521	46.660274	21.954110	3.409589	15.060959	2.758904	43.489041	6.321918	2007.815753	180921.195890
std	421.610009	42.300571	24.284752	9981.264932	1.382997	1.112799	30.202904	20.645407	181.066207	456.098091	...	125.338794	66.256028	61.119149	29.317331	55.757415	40.177307	496.123024	2.703626	1.328095	79442.502883
min	1.000000	20.000000	21.000000	1300.000000	1.000000	1.000000	1872.000000	1950.000000	0.000000	0.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	1.000000	2006.000000	34900.000000
25%	365.750000	20.000000	59.000000	7553.500000	5.000000	5.000000	1954.000000	1967.000000	0.000000	0.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	5.000000	2007.000000	129975.000000
50%	730.500000	50.000000	69.000000	9478.500000	6.000000	5.000000	1973.000000	1994.000000	0.000000	383.500000	...	0.000000	25.000000	0.000000	0.000000	0.000000	0.000000	0.000000	6.000000	2008.000000	163000.000000
75%	1095.250000	70.000000	80.000000	11601.500000	7.000000	6.000000	2000.000000	2004.000000	166.000000	712.250000	...	168.000000	68.000000	0.000000	0.000000	0.000000	0.000000	0.000000	8.000000	2009.000000	214000.000000
max	1460.000000	190.000000	313.000000	215245.000000	10.000000	9.000000	2010.000000	2010.000000	1600.000000	5644.000000	...	857.000000	547.000000	552.000000	508.000000	480.000000	738.000000	15500.000000	12.000000	2010.000000	755000.000000

	Id	MSSubClass	MSZoning	LotFrontage	LotArea	Street	Alley	LotShape	LandContour	Utilities	...	PoolQC	Fence	MiscFeature	MoSold	YrSold	SaleType	SaleCondition	SalePrice
0	1	60	RL	65.0	8450	Pave	NaN	Reg	Lvl	AllPub	...	NaN	NaN	NaN	2	2008	WD	Normal	208500
1	2	20	RL	80.0	9600	Pave	NaN	Reg	Lvl	AllPub	...	NaN	NaN	NaN	5	2007	WD	Normal	181500
2	3	60	RL	68.0	11250	Pave	NaN	IR1	Lvl	AllPub	...	NaN	NaN	NaN	9	2008	WD	Normal	223500
3	4	70	RL	60.0	9550	Pave	NaN	IR1	Lvl	AllPub	...	NaN	NaN	NaN	2	2006	WD	Abnorml	140000
4	5	60	RL	84.0	14260	Pave	NaN	IR1	Lvl	AllPub	...	NaN	NaN	NaN	12	2008	WD	Normal	250000

	Id	MSSubClass	MSZoning	LotFrontage	LotArea	Street	Alley	LotShape	LandContour	Utilities	...	PoolQC	Fence	MiscFeature	MoSold	YrSold	SaleType	SaleCondition	SalePrice
0	1	60	RL	65.0	8450	Pave	NaN	Reg	Lvl	AllPub	...	NA	NA	NA	2	2008	WD	Normal	208500
1	2	20	RL	80.0	9600	Pave	NaN	Reg	Lvl	AllPub	...	NA	NA	NA	5	2007	WD	Normal	181500
2	3	60	RL	68.0	11250	Pave	NaN	IR1	Lvl	AllPub	...	NA	NA	NA	9	2008	WD	Normal	223500
3	4	70	RL	60.0	9550	Pave	NaN	IR1	Lvl	AllPub	...	NA	NA	NA	2	2006	WD	Abnorml	140000
4	5	60	RL	84.0	14260	Pave	NaN	IR1	Lvl	AllPub	...	NA	NA	NA	12	2008	WD	Normal	250000

	Id	MSSubClass	MSZoning	LotFrontage	LotArea	Street	LotShape	LandContour	Utilities	LotConfig	...	PoolArea	PoolQC	Fence	MiscFeature	MiscVal	MoSold	YrSold	SaleType	SaleCondition	SalePrice
0	1	0.073732	RL	-0.229203	-0.207125	Pave	Reg	Lvl	AllPub	Inside	...	-0.068715	NA	NA	NA	-0.087718	-1.599030	0.138826	WD	Normal	208500
1	2	-0.871979	RL	0.451876	-0.091909	Pave	Reg	Lvl	AllPub	FR2	...	-0.068715	NA	NA	NA	-0.087718	-0.489318	-0.614137	WD	Normal	181500
2	3	0.073732	RL	-0.092987	0.073401	Pave	IR1	Lvl	AllPub	Inside	...	-0.068715	NA	NA	NA	-0.087718	0.990298	0.138826	WD	Normal	223500
3	4	0.310159	RL	-0.456229	-0.096918	Pave	IR1	Lvl	AllPub	Corner	...	-0.068715	NA	NA	NA	-0.087718	-1.599030	-1.367100	WD	Abnorml	140000
4	5	0.073732	RL	0.633497	0.374967	Pave	IR1	Lvl	AllPub	FR2	...	-0.068715	NA	NA	NA	-0.087718	2.100010	0.138826	WD	Normal	250000

هدف از انجام¶

توضیح کلی پروژه¶

داده‌های مورد استفاده¶

Phase 0¶

1¶

2¶

3¶

4¶

5¶

6¶

7¶

8¶

Phase 1¶

1¶

2¶

PoolQC, MiscFeature, Fence, FireplaceQu, GarageCond, GarageType, GarageFinish, GarageQual, BsmtExposure, BsmtFinType1, BsmtFinType2, BsmtCond, BsmtQual, MasVnrType¶

Alley¶

LotFrontage, GarageYrBlt, MasVnrArea¶

Electrical¶

3¶

4¶

5¶

6¶

Phase 2¶

KNN¶

Decision Tree¶

LinearRegression¶

3¶

4¶

Phase 3¶

1¶

2¶

3¶

نتیجه‌گیری کلی¶

منابع استفاده شده¶

	Id	OverallQual	YearBuilt	YearRemodAdd	MasVnrArea	ExterQual	ExterCond	BsmtQual	BsmtExposure	...	New	WD	Normal	Partial
254	255	-0.795596	-0.471824	-1.349529	-0.574672	3	2	4	4	...	0	1	1	0
1065	1066	0.650852	0.820028	0.588713	-0.574672	2	4	0	1	...	0	1	1	0
864	865	0.650852	1.184397	1.121729	-0.574672	2	4	0	4	...	1	0	0	1
798	799	2.097301	1.217521	1.170185	4.188586	0	4	0	4	...	1	0	0	1
380	381	-0.795596	-1.564930	-1.688721	-0.574672	3	4	4	4	...	0	1	1	0

	Id	OverallQual	YearBuilt	YearRemodAdd	MasVnrArea	ExterQual	ExterCond	BsmtQual	BsmtExposure	...	WD	Normal
1321	1322	-2.242045	-0.736820	-1.688721	-0.574672	3	4	3	3	...	1	1
836	837	-0.795596	-0.769944	-0.574232	-0.574672	3	4	4	4	...	0	1
413	414	-0.795596	-1.465557	-1.688721	-0.574672	3	4	4	4	...	1	1
522	523	-0.072372	-0.803069	-1.688721	-0.574672	3	2	4	4	...	1	1
1035	1036	-1.518821	-0.471824	-1.349529	-0.574672	3	2	3	3	...	1	1